Abstract: A system uses a neural network based model to perform scene text recognition. The system achieves high accuracy of prediction of text from scenes based on a neural network architecture that uses double attention mechanism. The neural network based model includes a convolutional neural network component that outputs a set of visual features and an attention extractor neural network component that determines attention scores based on the visual features. The visual features and the attention scores are combined to generate mixed features that are provided as input to a character recognizer component that determines a second attention score and recognizes the characters based on the second attention score. The system trains the neural network based model by adjusting the neural network parameters to minimize a multi-class gradient harmonizing mechanism (GHM) loss. The multi-class GHM loss varies based on a level of difficulty of the sample.

Abstract: The present invention discloses a control method, system, electronic device and readable storage medium for a capsule endoscope. The method includes: providing a working apparatus, comprising a capsule endoscope, and an external data recorder for cooperating with and controlling the capsule endoscope; monitoring the received ambient power by the external data recorder before wireless transmission of the capsule endoscope or during an intermittence between two transmissions, and/or monitoring the output power of the capsule endoscope by the external data recorder as data is transmitted during wireless transmission; adjusting the operating state of the working apparatus according to the ambient power and/or output power.

Abstract: A method for generating a neural network, including initializing the neural network including a plurality of cells, each cell corresponding to a graph including one or more nodes, each node corresponding to a latent representation of a dataset. A plurality of gates are generated, wherein each gate independently determines whether an operation between two nodes is used. A first regularization is performed using the plurality of gates. The first regularization is one of a group-structured sparsity regularization and a path-depth-wised regularization. An optimization is performed on the neural network by adjusting its network parameters and gate parameters based on the regularization of the sparsity.